Auflistung nach Autor:in "Wild, Peter"
1 - 5 von 5
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragCross-eyed - cross-spectral iris/periocular recognition database and competition(Biosig 2016, 2016) Sequeira, Ana F.; Chen, Lulu; Ferryman, James; Alonso-Fernandez, Fernando; Bigun, Josef; Raja, Kiran B.; Ramachandra, Raghavendra; Busch, Christoph; Wild, Peter
- KonferenzbeitragExperimental evidence of ageing in hand biometrics(BIOSIG 2013, 2013) Uhl, Andreas; Wild, PeterBiometric systems build upon the critical property of measuring behavioral, physiological or chemical human properties remaining stable over time. But both, the age of users and ageing of the user's template may affect performance due to the accumulation of personal changes and indirect behavioral effects like less accurate ability to present the biometric to the sensor. This paper compares short-timespan versus longtimespan effects on different hand-based features presenting the first high-resolution hand-ageing database and identifying features resistant and prone to ageing. Ageing goats, i.e. users responsible for low matching scores across features, are investigated and single-sensor multibiometrics is highlighted to target the ageing problem.
- KonferenzbeitragImage metric-based biometric comparators: a supplement to feature vector-based Hamming distance?(BIOSIG 2012, 2012) Hofbauer, Heinz; Rathgeb, Christian; Uhl, Andreas; Wild, PeterIn accordance with the ISO/IEC FDIS 19794-6 standard an iris-biometric fusion of image metric-based and Hamming distance (HD) comparison scores is presented. In order to demonstrate the applicability of a knowledge transfer from image quality assessment to iris recognition, Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Local Edge Gradients metric (LEG), Edge Similarity Score (ESS), Local Feature Based Visual Security (LFBVS), and Visual Information Fidelity (VIF) are applied to iris textures, i.e. query textures are interpreted as noisy representations of registered ones. Obtained scores are fused with traditional HD scores obtained from iris-codes generated by different feature extraction algorithms. Experimental evaluations on the CASIA-v3 iris database confirm the soundness of the proposed approach.
- TextdokumentIrisbiometrie in der Überwachung: Innovationen zu Segmentierung und Komparatoren(Ausgezeichnete Informatikdissertationen 2012, 2013) Wild, PeterDie Iris des menschlichen Auges zählt zu den eindeutigsten Merkmalen zur Personenidentifikation ohne Erfordernis von Token oder Wissen. Irisbiometrie-Systeme erfordern aber traditionell die Kooperation der Person dessen Merkmal extrahiert werden soll. Um aus Sicherheitsgründen die automatische Identitätsfeststellung aus Beobachtungsdaten zu ermöglichen, müssen neue Lösungen entwickelt und untersucht werden, um Eingabebeispiele niedriger Qualität (defokussierte, bewegungs-unscharfe, ausserhalb der optischen Achse aufgenommene Bilder verschiedener Spektren) in Echtzeit verarbeiten zu können. Diese Arbeit präsentiert neue Modelle zur homogenen Segmentierung von Bildern sichtbarer Wellenlänge sowie nahinfrarot und neue Komparatoren, welche die Wechselbeziehung zwischen Genauigkeit und Geschwindigkeit ausnutzen.
- KonferenzbeitragSegmentation-level fusion for iris recogntion(BIOSIG 2015, 2015) Wild, Peter; Hofbauer, Heinz; Ferryman, James; Uhl, AndreasThis paper investigates the potential of fusion at normalisation/segmentation level prior to feature extraction. While there are several biometric fusion methods at data/feature level, score level and rank/decision level combining raw biometric signals, scores, or ranks/decisions, this type of fusion is still in its infancy. However, the increasing demand to allow for more relaxed and less invasive recording conditions, especially for on-the-move iris recognition, suggests to further investigate fusion at this very low level. This paper focuses on the approach of multi-segmentation fusion for iris biometric systems investigating the benefit of combining the segmentation result of multiple normalisation algorithms, using four methods from two different public iris toolkits (USIT, OSIRIS) on the public CASIA and IITD iris datasets. Evaluations based on recognition accuracy and ground truth segmentation data indicate high sensitivity with regards to the type of errors made by segmentation algorithms.